© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54730
    Prev
    Next
    INDEX
    Explanations

    По

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheers
    -0.08
     lem
    -0.08
     Lem
    -0.08
    猴
    -0.08
    ouveau
    -0.08
    夫
    -0.08
     hübs
    -0.07
     décon
    -0.07
    踩
    -0.07
     lemma
    -0.07
    POSITIVE LOGITS
    Classification
    0.10
     classifications
    0.10
     категория
    0.09
    Тип
    0.09
     clasific
    0.09
     categ
    0.09
     classification
    0.09
     classific
    0.09
    类别
    0.09
    类型
    0.09
    Activations Density 0.070%

    No Known Activations